A Lightweight Convolutional Neural Network Based on Group-Wise Hybrid Attention for Remote Sensing Scene Classification

Abstract

With the development of computer vision, attention mechanisms have been widely studied. Although the introduction of an attention module into a network model can help to improve e classification performance on remote sensing scene images, the direct introduction of an attention module can increase the number of model parameters and amount of calculation, resulting in slower model operations. To solve this problem, we carried out the following work. First, a channel attention module and spatial attention module were constructed. The input features were enhanced through channel attention and spatial attention separately, and the features recalibrated by the attention modules were fused to obtain the features with hybrid attention. Then, to reduce the increase in parameters caused by the attention module, a group-wise hybrid attention module was constructed. The group-wise hybrid attention module divided the input features into four groups along the channel dimension, then used the hybrid attention mechanism to enhance the features in the channel and spatial dimensions for each group, then fused the features of the four groups along the channel dimension. Through the use of the group-wise hybrid attention module, the number of parameters and computational burden of the network were greatly reduced, and the running time of the network was shortened. Finally, a lightweight convolutional neural network was constructed based on the group-wise hybrid attention (LCNN-GWHA) for remote sensing scene image classification. Experiments on four open and challenging remote sensing scene datasets demonstrated that the proposed method has great advantages, in terms of classification accuracy, even with a very low number of parameters.

A Lightweight Convolutional Neural Network Based on Hierarchical-Wise Convolution Fusion for Remote-Sensing Scene Image Classification

“…As far as the number of parameters is concerned, the parameters of the proposed method are 0.6 M, which is 9.6% and 10% of that of the lightweight methods LCNN-BFF [32] and Skip-Connected CNN [42]. Compared with LCNN-GWHA [55], although the number of parameters is slightly increased, the classification accuracy of the proposed method has obvious advantages under both training ratios. [43] 90.82 ± 0.16 96.89 ± 0.10 130 M Fine-tuning [28] 86.59 ± 0.29 89.64 ± 0.36 130 M Skip-Connected CNN [42] 91.10 ± 0.15 93.30 ± 0.13 6 M LCNN-BFF [32] 91.66 ± 0.48 94.64 ± 0.16 6.2 M Gated Bidirectiona [40] 90.…”

“…Firstly, a gradient-weighted class activation map (Grad CAM) is utilized to visualize the proposed method. In order to prove that the proposed method can extract the significant features of remote-sensing images effectively, two methods, LCNN-BFF [32] and LCNN-GWHA [55], which have good classification performance, are chosen in the experiment for visual analysis on the UCM datasets. The visualization results are shown in Figure 14.…”

“…The highlighted areas in the gradient-weighted class activation graph indicate how much attention is paid to the scene by the proposed method, while red highlighted areas indicate a higher degree of attention to the scene. From Figure 14, it can be seen that compared with LCNN-BFF [32] and LCNN-GWHA [55], the proposed method can extract scene features more effectively and have a better semantic coverage for the scene area.…”

“…with LCNN-BFF [32] and LCNN-GWHA [55], the proposed method can extract scene features more effectively and have a better semantic coverage for the scene area.…”

Fuzzy Cognitive Maps with Bird Swarm Intelligence Optimization-Based Remote Sensing Image Classification

“…Figure 7 examines the comparison study of the FCMBS-RSIC technique with recent methods [ 23 ] under training/testing (80 : 20) data of UCM21 dataset. The experimental results revealed that the D-CNN, SC-CNN, and VGG-VD16-SAFF techniques have gained ineffective outcomes with the least values of prec n , reca l , and accu y .…”